Update README.md

README.md

@@ -35,7 +35,7 @@ For those who are interested in model conversion, you can try to export axmodel
 |------|------|
 | llm prefill ( input_token_num + prompt_token_num 在 [0,128 ] ) | 104 ms  | 
 | llm prefill ( input_token_num + prompt_token_num 在 [128,256 ] ) | 234 ms  | 
-| Decode  |  21.24 token/s token/s |
+| Decode  |  21.24 token/s |
 
 ## How to use